© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74866
    Prev
    Next
    INDEX
    Explanations

    combinations of concepts or elements that imply risk or effectiveness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hiba
    -0.07
    unya
    -0.07
     ÙĪØ§ÙĦع
    -0.07
     bindActionCreators
    -0.06
    ombat
    -0.06
    isay
    -0.06
    İ
    -0.06
    ietet
    -0.06
    ез
    -0.06
    connexion
    -0.06
    POSITIVE LOGITS
     combo
    0.13
     combination
    0.13
     Combination
    0.12
     resulting
    0.11
    combo
    0.11
     combos
    0.11
     Together
    0.10
     combinations
    0.10
     resultant
    0.10
     Combo
    0.10
    Activations Density 0.043%

    No Known Activations